Predictive tools as part of decission aiding processes at the airport – the case of Facebook Prophet library

• Autorzy: Korga Sylwester , Żyła Kamil , Józwik Jerzy , Pytka Jarosław , Cybul Kamil

Identyfikatory

DOI

10.35784/acs-2023-35

• Języki publikacji: EN

Abstrakty

EN

Prophet is a quite fresh and promising open-source library for machine learning, developed by Facebook, that gains some significant interest. It could be used for predicting time series taking into account holidays and seasonality effects. Its possible applications and deficit of scientific works concerning its usage within decision processes convinced the authors to state the research question, if the Prophet library could provide reliable prediction to support decision-making processes at the airport. The case of Radawiec airport (located near Lublin, Poland) was chosen. Official measurement data (from the last 4 years) published by the Polish Government Institute was used to train the neural network and predict daily averages of wind speed, temperature, pressure, relative humidity and rainfall totals during the day and night. It was revealed that most of the predicted data points were within the acceptance threshold, and computations were fast and highly automated. However, the authors believe that the Prophet library is not particularly useful for airport decision-making processes because the way it handles additional regressors and susceptibility to unexpected phenomena negatively affects the reliability of prediction results.

Słowa kluczowe

EN

weather prediction; Facebook Prophet; aviation; machine learning; data analysis

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2023
• Tom: Vol. 19, no 4
• Strony: 51--67
• Opis fizyczny: Bibliogr. 31 poz., fig., tab.

Twórcy

autor

Korga Sylwester

• Lublin University of Technology, Faculty of Electrical Engineering and Computer Science, Department of Computer Science, Poland

• https://orcid.org/0009-0001-4849-5079

autor

Żyła Kamil

• Lublin University of Technology, Faculty of Electrical Engineering and Computer Science, Department of Computer Science, Poland

• https://orcid.org/0000-0003-4505-980X

autor

Józwik Jerzy

• Lublin University of Technology, Faculty of Mechanical Engineering, Department of Production Engineering, Poland

• https://orcid.org/0000-0002-3506-2741

autor

Pytka Jarosław

• Lublin University of Technology, Faculty of Mechanical Engineering, Department of Motor Vehicles, Lublin, Poland

• https://orcid.org/0000-0002-5181-2872

autor

Cybul Kamil

• Lublin University of Technology, Doctoral School of the Lublin University of Technology

Bibliografia

• [1] Akula, R., Wieselthier, Z., Martin, L., & Garibay, I. (2019). Forecasting the success of television series using machine learning. ArXiv, abs/1910.12589. https://doi.org/10.48550/arXiv.1910.12589
• [2] Asha, J., Rishidas, S., SanthoshKumar, S., & Reena, P. (2020). Analysis of temperature prediction using random forest and Facebook Prophet algorithms. Lecture Notes on Data Engineering and Communications Technologies, 46, 432-439. https://doi.org/10.1007/978-3-030-38040-3_49
• [3] Banga, A., Ahuja, R., & Sharma, S. C. (2021). Stacking machine learning models to forecast hourly and daily electricity consumption of household using Internet of Things. Journal Of Scientific & Industrial Research, 80, 894-904.
• [4] Bendiek, P., Taha, A., Abbasi, Q. H., & Barakat, B. (2022). Solar irradiance forecasting using a data-driven algorithm and contextual optimisation. Applied Sciences, 12(1), 134. https://doi.org/10.3390/app12010134
• [5] Dee, D. P., Uppala, S. M., Simmons, A. J., Berrisford, P., Poli, P., Kobayashi, S., Andrae, U., Balmaseda, M. A., Balsamo, G., Bauer, P., Bechtold, P., Beljaars, A. C. M., Van De Berg, L., Bidlot, J., Bormann, N., Delsol, C., Dragani, R., Fuentes, M., Geer, A. J., … Vitart, F. (2011). The ERA‐Interim reanalysis: Configuration and performance of the data assimilation system. Quarterly Journal of the Royal Meteorological Society, 137(656), 553–597. https://doi.org/10.1002/qj.828
• [6] El Hachimi, C., Belaqziz, S., Khabba, S., & Chehbouni, A. (2021). Towards precision agriculture in Morocco: A machine learning approach for recommending crops and forecasting weather. 2021 International Conference on Digital Age & Technological Advances for Sustainable Development (ICDATA) (pp. 88–95). IEEE. https://doi.org/10.1109/ICDATA52997.2021.00026
• [7] Garlapati, A., Krishna, D. R., Garlapati, K., Srikara Yaswanth, N. M., Rahul, U., & Narayanan, G. (2021). Stock Price Prediction Using Facebook Prophet and Arima Models. 2021 6th International Conference for Convergence in Technology (I2CT) (pp. 1–7). IEEE. https://doi.org/10.1109/I2CT51068.2021.9418057
• [8] Haq, M. A. (2022). CDLSTM: A novel model for climate change forecasting. Computers Materials & Continua, 71(2), 2363-2381. https://doi.org/10.32604/cmc.2022.023059
• [9] IMGW. (2022). Homepage of the Institute of Meteorology and Water Management - National Research Institute. https://www.imgw.pl
• [10] Junsuk, K., & Tae, J. K. (2021). Application of Facebook’s Prophet model for forecasting meteorological data. Journal of the Korean Society of Hazard Mitigation, 21(2), 53-58. https://doi.org/10.9798/KOSHAM.2021.21.2.53
• [11] Keras. (2023). Keras library homepage. https://keras.io
• [12] Krieger, M. (2021, February 20). Time series analysis with Facebook Prophet: How it works and how to use it. https://towardsdatascience.com
• [13] Mitchell, T. M. (1997). Machine learning. McGraw-Hill Science.
• [14] Narmeen, M., Sattar, M. U., Khan, H. W., Fatima, M., Azad, M.-D., & Ghani, F. (2022). Impact of Weather on COVID-19 in Metropolitan Cities ofPakistan: A Data-Driven Approach. International Journal of Computing and Digital Systems, 11(1), 905–915. https://doi.org/10.12785/ijcds/110174
• [15] Oo, Z. Z., & Phyu, S. (2019). Microclimate Prediction Using Cloud Centric Model Based on IoT Technology for Sustainable Agriculture. 2019 IEEE 4th International Conference on Computer and Communication Systems (ICCCS) (pp. 660–663). IEEE. https://doi.org/10.1109/CCOMS.2019.8821705
• [16] Ortiz-Bejar, J., Ortiz-Bejar, J., Zamora-Mendez, A., Pineda-Garcia, G., Graff, M., & Tellez, E. S. (2020). Forecasting without context problem. 2020 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC) (pp. 1–6). IEEE. https://doi.org/10.1109/ROPEC50909.2020.9258744
• [17] Papacharalampous, G., Tyralis, H., & Koutsoyiannis, D. (2018). Predictability of monthly temperature and precipitation using automatic time series forecasting methods. Acta Geophysica, 66, 807-831. https://doi.org/10.1007/s11600-018-0120-7
• [18] Patil, S., & Pandya, S. (2021). Forecasting dengue hotspots associated with variation in meteorological parameters using regression and time series models. Frontiers in Public Health, 9, 798034. https://doi.org/10.3389/fpubh.2021.798034
• [19] Prophet. (2022). Seasonality, holiday effects, and regressors. https://facebook.github.io/prophet/docs/seasonality,_holiday_effects,_and_regressors.html
• [20] Prophet. (2023). Facebook Prophet library homepage. https://facebook.github.io/prophet/
• [21] Qiu, Q., He, J., Chen, H., & Qiu, J. (2019). Research on the evolution law of emergency network public opinion. 2019 12th International Symposium on Computational Intelligence and Design (ISCID) ( pp. 157–161). IEEE. https://doi.org/10.1109/ISCID.2019.10119
• [22] Ryu, S., Nam, H. J., Kim, J. M., & Kim, S. W. (2021). Current and future trends in hospital utilization of patients with schizophrenia in Korea: A time series analysis using national health insurance data. Psychiatry Investigation, 18(8), 795-800. https://doi.org/10.30773/pi.2021.0071
• [23] Shenbagalakshmi, V., & Jaya, T. (2022). Application of machine learning and IoT to enable child safety at home environment. Journal of Supercomputing, 78, 10357–10384. https://doi.org/10.1007/s11227-022-04310-z
• [24] Soltaganov, N. A., Sherstnev, V. S., Sherstneva, A. I., Botygin, I. A., & Krutikov, V. A. (2018). Construction of predictive models of meteorological parameters of the atmospheric surface layer. IOP Conference Series: Earth and Environmental Science, 211, 012027. https://doi.org/10.1088/1755-1315/211/1/012027
• [25] Sulasikin, A., Nugraha, Y., Kanggrawan, J. I., & Suherman, A. L. (2021). Monthly rainfall prediction using the Facebook Prophet model for flood mitigation in central Jakarta. 2021 International Conference on ICT for Smart Society (ICISS) (pp. 1-5). IEEE. https://doi.org/10.1109/ICISS53185.2021.9532507
• [26] Taylor, S. J., & Letham, B. (2018). Forecasting at scale. The American Statistician, 72(1), 37-45. https://doi.org/10.1080/00031305.2017.1380080
• [27] TensorFlow. (2023). TensorFlow library homepage. https://www.tensorflow.org
• [28] Thiyagarajan, K., Kodagoda, S., Ulapane, N., & Prasad, M. (2020). A temporal forecasting driven approach ysing facebook’s prophet method for anomaly detection in sewer air temperature sensor system. 2020 15th IEEE Conference on Industrial Electronics and Applications (ICIEA) (pp. 25–30). IEEE. https://doi.org/10.1109/ICIEA48937.2020.9248142
• [29] Toharudin, T., Pontoh, R. S., Caraka, R. E., Zahroh, S., Lee, Y., & Chen, R. C. (2021). Employing long short-term memory and Facebook prophet model in air temperature forecasting. Communications in Statistics-Simulation and Computation, 52(2), 279-290. https://doi.org/10.1080/03610918.2020.1854302
• [30] Urząd Lotnictwa Cywilnego. (2022). Meteorological service for international air navigation. Annex 3 to the Convention on International Civil Aviation. https://www.ulc.gov.pl/_download/prawo/prawo_miedzynarodowe/konwencje/Zal%C4%85cznik_3_cz_I_cz_II.pdf
• [31] Weytjens, H., Lohmann, E., & Kleinsteuber, M. (2021). Cash flow prediction: MLP and LSTM compared to ARIMA and Prophet. Electronic Commerce Research, 21, 371-391. https://doi.org/10.1007/s10660-019-09362-7